Exploring the Benefits of Visual Prompting in Differential Privacy. (arXiv:2303.12247v1 [cs.CV])

Visual Prompting (VP) is an emerging and powerful technique that allows
sample-efficient adaptation to downstream tasks by engineering a well-trained
frozen source model. In this work, we explore the benefits of VP in
constructing compelling neural network classifiers with differential privacy
(DP). We explore and integrate VP into canonical DP training methods and
demonstrate its simplicity and efficiency. In particular, we discover that VP
in tandem with PATE, a state-of-the-art DP training method that leverages the
knowledge transfer from an …

benefits canonical differential privacy discover efficiency emerging engineering integrate network neural network privacy tandem training work